© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 79071
    Prev
    Next
    INDEX
    Explanations

    noble and Nobel Prize recipients

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     vectores
    -0.82
    法則
    -0.81
     Almighty
    -0.76
    ỡng
    -0.76
     élimin
    -0.75
    大切
    -0.72
    toHaveBeen
    -0.72
    Strongly
    -0.71
     ด
    -0.71
     Б
    -0.71
    POSITIVE LOGITS
     laure
    1.09
     Noble
    1.01
    Noble
    0.97
     Savage
    0.93
     savage
    0.93
     steed
    0.92
     noble
    0.91
     चला
    0.88
     savages
    0.86
    chairs
    0.85
    Activations Density 0.016%

    No Known Activations